DiffServ中基于优先级的队列调度算法

为了提高DWRR算法的时延性能及应对突发流的能力,文中结合比例时延区分服务模型,在DWRR算法的基础上提出了一种能够体现优先级的队列调度算法-PDDRR。该算法的控制目标是保证各业务流的平均排队时延在无突发业务流时维持在给定的比率,而在应对突发流时忽略时延的比例公平原则,根据网络实时负载动态地调整各队列的权值,合理地分配资源。仿真结果表明,算法不仅能实现不同优先级业务的时延区分,而且在业务流突发时为各等级业务提供服务质量保证。     

融合外部属性的短时交通流预测研究

针对现有交通流量预测算法大多仅考虑常态下的预测,而未考虑天气属性、周围地理属性对预测结果的影响,提出一种融合外部属性的组合预测模型（A-STIGCN）。首先,将外部属性作为路网中路段的属性,同时对路段的属性和交通特征进行建模,得到增强的特征向量。其次,采用图小波变换和自适应矩阵分别提取交通流局部和全局空间特征信息,并借助门控循环单元（GRU）对时间信息的长时记忆能力以提取其时间特性。最后,通过注意力机制来捕获时空动态变化性进行交通流预测。采用深圳出租车轨迹数据、对应天气数据以及POI数据进行预测,研究结果表明：A-STIGCN组合模型预测效果优于传统线性模型及变体模型,与未引入注意力机制的ASTGCN模型相比,MAE降低了约0.131,精度提高了0.068,与未引入外部因素的TGCN模型对比分析,MAPE降低了约0.637%,精度提高了0.079,从而更好地为交通管理提供指导意见。     

Semisupervised Encrypted Traffic Identification Based on Auxiliary Classification Generative Adversarial Network

The rapidly increasing popularity of mobile devices has changed the methods with which people access various network services and increased network traffic markedly. Over the past few decades, network traffic identification has been a research hotspot in the field of network management and security monitoring. However, as more network services use encryption technology, network traffic identification faces many challenges. Although classic machine learning methods can solve many problems that cannot be solved by port- and payload-based methods, manually extract features that are frequently updated is time-consuming and labor-intensive. Deep learning has good automatic feature learning capabilities and is an ideal method for network traffic identification, particularly encrypted traffic identification; Existing recognition methods based on deep learning primarily use supervised learning methods and rely on many labeled samples. However, in real scenarios, labeled samples are often difficult to obtain. This paper adjusts the structure of the auxiliary classification generation adversarial network (ACGAN) so that it can use unlabeled samples for training, and use the wasserstein distance instead of the original cross entropy as the loss function to achieve semisupervised learning. Experimental results show that the identification accuracy of ISCX and USTC data sets using the proposed method yields markedly better performance when the number of labeled samples is small compared to that of convolutional neural network (CNN) based classifier.     

高速网络流量管理系统研究

随着互联网用户的不断增加和用户需求的不断变化,互联网上的应用类型也在发生着日新月异的变化。各种类型的业务流量不断增长,网络的负担不断加重,网络管理的难度也随之增加。如何通过合适的流量管理技术,即网络应用协议的识别与带宽管理技术,来协调网络应用与安全、带宽增长与业务收益、网络扩容与用户体验之间的关系,是网络管理者与运营者亟待解决的重要挑战。文章的研究便着重于此,首先介绍了网络流量管理的基本概念与关键技术,随后对主流的开源流量管理系统和商用流量管理系统进行介绍。最后提出了一种协同式的分布流量管理系统,分布式的部署流量管理子系统通过分析控制中心协同检测与管理流量,可以有效的提高网络流量管理效率,提高未知网络协议的识别率,能够有效检测和防止DDos攻击。     

空管系统中键盘快捷功能的研究与实现

目前国内空中交通管制系统人机界面的操作越来越趋于人性化,从可用、能用到好用的人机界面发展过程中,软件提供快捷的功能和方便的操作流程起到了很重要的作用,因此研究软件开发对键盘快捷键的支持就显得尤其重要。本文对可以实现的方法进行比较,分析实现方法的优劣,提出了一种实现键盘快捷功能的方法。     

From ethnographic record to system design

This paper explores the issues involved in moving from ethnographic explorations of work in context to a practical contribution to system design. It does so using the example of an interdisciplinary research project involving sociologists and computer scientists in the domain of air traffic control systems. It forms a pair with another paper (Sommerville et al., 1992) exploring these questions from the perspective of our computer science partners. We characterise ethnography as a research method, and consider the differences between undertaking it for strictly sociological or anthropological purposes by contrast with interdisciplinary and design purposes. We summarise some of our results in ethnographic explications of the work of air traffic controllers, and the sociality which it manifests. We describe the dialogues involved in rendering these observations informative for systems design, and the mutual translations implied in attempting to reconcile sociological with software engineering questions about supporting the work. We conclude by specifying some features of cooperative work which an engineering approach is in danger of overlooking; the ways, and limits, in which ethnographers can form a bridge between users and designers; and some of the conflicts of interest entrained in generating technical change.The research is funded by the UK MRC/SERC/ESRC Cognitive Science/HCI Initiative with the title Social Analysis of Control Systems for HCI Design, grant number SPG 8931598. The computer science partners are Professor Ian Sommerville, Dr Tom Rodden, Dr Pete Sawyer and Mr Richard Bentley. Thanks are due to Val King, Kjeldt Schmidt, Ian Sommerville and Tom Rodden for very helpful comments on earlier drafts of this paper.     

专用电话系统集中录音方案

数字录音系统是进行核对和事故追忆与分析的重要设备,目前,轨道交通数字录音系统普遍存在着录音信息不全或造价高昂的问题,在分析专用电话系统的组成及录音现状的基础上,提出了对专用电话系统的集中录音方案,介绍了集中录音的系统原理及特点,证明了集中录音能够满足专用电话系统对重要终端录音的需要。     

改进的退避算法在战术业务流中应用研究

研究战术的网络业务流问题。针对传统的网络退避算法由于网络信道访问频率过大,容易造成节点缓存队列拥塞等问题,特别是退避算法中的参数选择问题严重影响网络性能传输。提出了一种改进的退避算法应用于战术网络业务流中。改进的算法首先为结点引入适当的竞争系数,使得对于信道的访问可以根据当前网络的突发状态合理分派,同时根据网络状态和冲突节点发生情况,对竞争窗口大小分别采用线性和多重下降等方式进行动态调整,有效地改善网络的性能。仿真结果表明,改进后的退避算法具有较好的性能,有效降低了网络信道访问冲突发生概率,提高了网络系统的吞吐量。     

基于交通信息和配电网全成本电价的电动汽车充电负荷调度方法

电动汽车的集中充电行为会在一定程度造成交通拥堵,为解决这一问题,综合考虑交通信息和电网信息,基于边际定价理论得到配电网节点边际电价和交通阻塞成本,构建电动汽车充电的全成本电价模型。在此基础上,提出一种考虑交通信息和配电网全成本电价的电动汽车充电负荷调度方法。通过仿真算例验证,该方法在满足电动汽车充电需求的同时可以有效缓解交通拥堵。     

西南山区交通工程弃渣的工程特性评价及其分类

山区交通工程弃渣力学参数的准确测定,一直是弃渣场边坡稳定性评价面临的基础科学问题。在山区交通工程弃渣场运行特点和弃渣固体废弃物特征认知的基础上,探讨弃渣取样和试验代表性问题的物理根源,依托实际工程累计数据尝试提出简单实用的弃渣工程特性评价和分类方法。结果表明:①常规交通工程弃渣的密度、颗粒分析和强度试验,由于弃渣的粒径范围差异大、颗粒空间分布不均、弃渣来源复杂等固体废弃物特征造成取样和试验代表性难题; 用多阶段坡角测量和颗粒分析试验代替传统的弃渣边坡试验,解决了试验和取样代表性难题。②利用弃渣粗细比可将弃渣分为细粒弃渣、混合型弃渣和粗粒弃渣。③根据弃渣粗细比、天然休止角和整形坡率,将西南山区交通工程弃渣分为细粒弃渣、混合型弃渣和粗粒弃渣等3类。细粒弃渣,弃渣粗细比小于0.3,天然休止角小于31.5°,整形坡率为1.00:2.00; 混合型弃渣,弃渣粗细比为0.3～1.0,天然休止角为31.5°～39.5°,整形坡率为1.00:2.00～1.00:1.50; 粗粒弃渣,弃渣粗细比大于1.0,天然休止角大于39.5°,整形坡率为1.00:1.50。④用多阶段坡角测量、颗粒分析试验和无黏性土边坡稳定性系数计算公式代替传统的弃渣边坡试验和稳定性系数计算方法,方法简单,结果保守,可以作为弃渣边坡稳定性评价和安全控制技术的有益补充。